def __init__(self):
# INPUTY
self.buildingType = ctrl.Antecedent(np.arange(0, 400, 1), "Technologia budynku")
self.wearWater = ctrl.Antecedent(np.arange(0, 500, 0.1), "Zuzycie wody na osobe")
self.zone = ctrl.Antecedent(np.arange(15, 25, 0.01), "Strefa klimatyczna")
self.isolation = ctrl.Antecedent(np.arange(1, 100, 1), "Procentowa termoizolacja budynku")
self.surface = ctrl.Antecedent(np.arange(20, 150, 0.01), "Powierzchnia grzewcza")
# OUTPUTY
self.typeFurnance = ctrl.Consequent(np.arange(1, 100, 1), "Rodzaj pieca")
# MEMBERSHIPS FUN
self.buildingType['starebudownictwo'] = fuzz.trapmf(self.buildingType.universe, [170, 350, 400, 400])
self.buildingType['70-85'] = fuzz.gaussmf(self.buildingType.universe, 260, 25)
self.buildingType['86-92'] = fuzz.gaussmf(self.buildingType.universe, 200, 20)
self.buildingType['93-97'] = fuzz.gaussmf(self.buildingType.universe, 160, 15)
self.buildingType['98-07'] = fuzz.gaussmf(self.buildingType.universe, 120, 15)
self.buildingType['energooszczedny'] = fuzz.gaussmf(self.buildingType.universe, 80, 15)
self.buildingType['niskoenegetyczny'] = fuzz.gaussmf(self.buildingType.universe, 45, 10)
self.buildingType['pasywny'] = fuzz.trapmf(self.buildingType.universe, [0, 0, 15, 100])
# ----------------------
self.wearWater['1 osoba'] = fuzz.zmf(self.wearWater.universe, 20, 80)
self.wearWater['2 osoba'] = fuzz.gaussmf(self.wearWater.universe, 100, 30)
self.wearWater['3 osoba'] = fuzz.gaussmf(self.wearWater.universe, 150, 30)
self.wearWater['4 osoba'] = fuzz.gaussmf(self.wearWater.universe, 200, 40)
self.wearWater['5 osoba'] = fuzz.gaussmf(self.wearWater.universe, 250, 50)
self.wearWater['6 osoba'] = fuzz.gaussmf(self.wearWater.universe, 300, 60)
self.wearWater['7 osoba'] = fuzz.gaussmf(self.wearWater.universe, 350, 60)
self.wearWater['8 osoba'] = fuzz.smf(self.wearWater.universe, 310, 470)
# ----------------------
self.zone['Strefa 1'] = fuzz.gaussmf(self.zone.universe, 16, 0.5)
self.zone['Strefa 2'] = fuzz.gaussmf(self.zone.universe, 18, 0.9)
self.zone['Strefa 3'] = fuzz.gaussmf(self.zone.universe, 20, 1.5)
self.zone['Strefa 4'] = fuzz.gaussmf(self.zone.universe, 22, 1.2)
self.zone['Strefa 5'] = fuzz.gaussmf(self.zone.universe, 24, 0.45)
# ---------------------
self.surface['kawalerka'] = fuzz.zmf(self.surface.universe, 25, 65)
self.surface['mieszkanie'] = fuzz.gaussmf(self.surface.universe, 75, 30)
self.surface['apartament'] = fuzz.gaussmf(self.surface.universe, 111, 8)
self.surface['dom_jednorodzinny'] = fuzz.gaussmf(self.surface.universe, 130, 3.5)
self.surface['willa'] = fuzz.smf(self.surface.universe, 130, 150)
# --------------------
self.isolation['brak'] = fuzz.zmf(self.isolation.universe, 5, 15)
self.isolation['slabo'] = fuzz.gaussmf(self.isolation.universe, 20, 7)
self.isolation['srednio'] = fuzz.gaussmf(self.isolation.universe, 50, 20)
self.isolation['dobrze'] = fuzz.gaussmf(self.isolation.universe, 70, 10)
self.isolation['doskonale'] = fuzz.smf(self.isolation.universe, 75, 95)
self.typeFurnance['weglowy'] = fuzz.zmf(self.typeFurnance.universe, 4, 40)
self.typeFurnance['gazowy'] = fuzz.gbellmf(self.typeFurnance.universe, 23, 2.5, 50)
self.typeFurnance['pompa ciepla'] = fuzz.smf(self.typeFurnance.universe, 70, 100)
# -----------------------
# RULES
rules = [
ctrl.Rule(self.buildingType['pasywny'] & self.wearWater['4 osoba'] & self.surface['dom_jednorodzinny'] &
self.isolation['doskonale'], self.typeFurnance['pompa ciepla']),
ctrl.Rule(self.buildingType['starebudownictwo'] & self.wearWater['8 osoba'] & self.isolation['brak'] &
self.surface['dom_jednorodzinny'],
self.typeFurnance['weglowy']),
ctrl.Rule(self.buildingType['starebudownictwo'] & self.wearWater['7 osoba'] & self.isolation['slabo'] &
self.surface['dom_jednorodzinny'],
self.typeFurnance['weglowy']),
ctrl.Rule(self.buildingType['starebudownictwo'] & self.wearWater['6 osoba'] & self.isolation['slabo'] &
self.surface['dom_jednorodzinny'],
self.typeFurnance['weglowy']),
ctrl.Rule(self.buildingType['70-85'] & self.wearWater['6 osoba'] & self.isolation['slabo'] & self.surface[
'dom_jednorodzinny'],
self.typeFurnance['weglowy']),
ctrl.Rule(self.buildingType['niskoenegetyczny'] & self.wearWater['5 osoba'] & self.isolation['dobrze'] &
self.surface['dom_jednorodzinny'] | self.surface['willa'], self.typeFurnance['pompa ciepla']),
ctrl.Rule(self.buildingType['energooszczedny'] & self.wearWater['5 osoba'] & self.isolation['dobrze'] &
self.surface['dom_jednorodzinny'] | self.surface['willa'], self.typeFurnance['pompa ciepla']),
ctrl.Rule(self.buildingType['energooszczedny'] & self.wearWater['4 osoba'] & self.isolation['dobrze'] &
self.surface['dom_jednorodzinny'] | self.surface['willa'], self.typeFurnance['pompa ciepla']),
ctrl.Rule(self.buildingType['niskoenegetyczny'] & self.wearWater['5 osoba'] & self.isolation['dobrze'] &
self.surface['dom_jednorodzinny'] | self.surface['willa'], self.typeFurnance['pompa ciepla']),
ctrl.Rule(self.buildingType['93-97'] & self.wearWater['2 osoba'] & self.isolation['srednio'] & self.surface[
'kawalerka'], self.typeFurnance['gazowy']),
ctrl.Rule(self.buildingType['93-97'] & self.wearWater['3 osoba'] & self.isolation['srednio'] & self.surface[
'mieszkanie'], self.typeFurnance['gazowy']),
ctrl.Rule(self.buildingType['93-97'] & self.wearWater['4 osoba'] & self.isolation['srednio'] & self.surface[
'mieszkanie'], self.typeFurnance['gazowy']),
ctrl.Rule(self.buildingType['98-07'] & self.wearWater['2 osoba'] & self.isolation['srednio'] & self.surface[
'kawalerka'], self.typeFurnance['gazowy']),
ctrl.Rule(self.buildingType['98-07'] & self.wearWater['3 osoba'] & self.isolation['srednio'] & self.surface[
'mieszkanie'], self.typeFurnance['gazowy']),
ctrl.Rule(self.buildingType['98-07'] & self.wearWater['4 osoba'] & self.isolation['srednio'] & self.surface[
'mieszkanie'], self.typeFurnance['gazowy']),
ctrl.Rule(self.buildingType['98-07'] & self.wearWater['5 osoba'] & self.isolation['srednio'] & self.surface[
'apartament'], self.typeFurnance['gazowy']),
]
# Controll System
self.typeControl = ctrl.ControlSystem(rules)
self.type = ctrl.ControlSystemSimulation(self.typeControl)
def __init__(self,
minm,
maxm,
n_variavel,
media=None,
dp=None,
dados=None,
passo=0.01,
likert=3,
tipo='antecedente'):
# dados: vetor de dados de referência.
# minm: valor mínimo.git init.
# maxm: valor máximo.
# n_variavel: nome da variavel.
# passo: nível de discretização da variável fuzzy.
# tipo: tipo de variável fuzzy.
# likert: tamanho da escala.
self.min = minm
self.max = maxm
# Calcula a média e desvio padrão a partir dos dados fornecidos,
# caso contrário os estima a partir dos valores mínimo e máximo.
try:
self.media = dados.mean()
self.dp = dados.std()
media = self.media
dp = self.dp
except Exception:
try:
self.media = media * 1
self.dp = dp * 1
except Exception:
self.media = (minm + maxm) / 2
self.dp = ((maxm - minm)**2 / 12)**0.5
media = self.media
dp = self.dp
if tipo == 'consequente':
self.vf = ctrl.Consequent(np.arange(minm, maxm, passo), n_variavel)
else:
self.vf = ctrl.Antecedent(np.arange(minm, maxm, passo), n_variavel)
if (likert == 5):
self.vf['muito baixo'] = fuzz.zmf(self.vf.universe, media - 5 * dp,
media - 2 * dp)
self.vf['baixo'] = fuzz.gaussmf(self.vf.universe, media - 2 * dp,
dp)
self.vf['medio'] = fuzz.gaussmf(self.vf.universe, media, dp)
self.vf['alto'] = fuzz.gaussmf(self.vf.universe, media + 2 * dp,
dp)
self.vf['muito alto'] = fuzz.smf(self.vf.universe, media + 2 * dp,
media + 5 * dp)
elif (likert == 3):
self.vf['baixo'] = fuzz.zmf(self.vf.universe, minm, media)
self.vf['medio'] = fuzz.gaussmf(self.vf.universe, media, dp)
self.vf['alto'] = fuzz.smf(self.vf.universe, media, maxm)
else:
raise RuntimeError(
"Utilize escalas tipo likert com 3 ou 5 categorias.")
def __init__(self, parameter, x_minSOC_range, x_E_range, y_alpha_range):
# 创建一个模糊控制变量
self.x_minSOC = ctrl.Antecedent(x_minSOC_range, 'minSOC')
self.x_E = ctrl.Antecedent(x_E_range, 'E')
self.y_alpha = ctrl.Consequent(y_alpha_range, 'alpha')
# 定义了模糊集及其隶属度函数
self.x_minSOC['NB'] = fuzz.zmf(x_minSOC_range, parameter['x_min_zmf10'], parameter['x_min_zmf11'])
self.x_minSOC['NS'] = fuzz.trimf(x_minSOC_range, parameter['x_min_trimf1'])
self.x_minSOC['ZO'] = fuzz.trimf(x_minSOC_range, parameter['x_min_trimf2'])
self.x_minSOC['PS'] = fuzz.trimf(x_minSOC_range, parameter['x_min_trimf3'])
self.x_minSOC['PB'] = fuzz.smf(x_minSOC_range, parameter['x_min_smf10'], parameter['x_min_smf11'])
self.x_E['NB'] = fuzz.zmf(x_E_range, parameter['x_E_zmf10'], parameter['x_E_zmf11'])
self.x_E['PB'] = fuzz.smf(x_E_range, parameter['x_E_smf10'], parameter['x_E_smf11'])
self.y_alpha['NB'] = fuzz.zmf(y_alpha_range, parameter['y_zmf10'], parameter['y_zmf11'])
self.y_alpha['NS'] = fuzz.trimf(y_alpha_range, parameter['y_trimf1'])
self.y_alpha['ZO'] = fuzz.trimf(y_alpha_range, parameter['y_trimf2'])
self.y_alpha['PS'] = fuzz.trimf(y_alpha_range, parameter['y_trimf3'])
self.y_alpha['PB'] = fuzz.smf(y_alpha_range, parameter['y_smf10'], parameter['y_smf11'])
self.y_alpha['NB1'] = fuzz.zmf(y_alpha_range, parameter['y_zmf20'], parameter['y_zmf21'])
self.y_alpha['PB1'] = fuzz.trimf(y_alpha_range, parameter['y_trimf4'])
# 设置输出alpha去模糊方法-质心去模糊方法
self.y_alpha.defuzzify_method = 'mom'
self.system = None
self.sim = None
def consecuentes():
agua = ctrl.Consequent(
[0, 30, 60, 90, 120, 150, 200, 250, 300, 350, 400, 450], 'agua')
cafe = ctrl.Consequent(np.arange(0, 151, 1), 'cafe')
leche = ctrl.Consequent(np.arange(0, 58, 1), 'leche')
chocolate = ctrl.Consequent(np.arange(0, 15, 1), 'chocolate')
tiempo = ctrl.Consequent(np.arange(1, 4.5, 0.5), 'tiempo')
agua['poca'] = fuzz.zmf(agua.universe, 90, 300)
agua['media'] = fuzz.trimf(agua.universe, [125, 250, 350])
agua['mucha'] = fuzz.smf(agua.universe, 200, 345)
cafe['poca'] = fuzz.zmf(cafe.universe, 45, 76)
cafe['media'] = fuzz.trimf(cafe.universe, [45, 75, 100])
cafe['mucha'] = fuzz.smf(cafe.universe, 74, 100)
leche['poca'] = fuzz.zmf(leche.universe, 14, 29)
leche['media'] = fuzz.trimf(leche.universe, [14, 28, 42])
leche['mucha'] = fuzz.smf(leche.universe, 27, 42)
chocolate['poca'] = fuzz.zmf(chocolate.universe, 4, 8)
chocolate['media'] = fuzz.trimf(chocolate.universe, [4, 7, 10])
chocolate['mucha'] = fuzz.smf(chocolate.universe, 6, 10)
tiempo['poca'] = fuzz.zmf(tiempo.universe, 1.5, 3.0)
tiempo['media'] = fuzz.trimf(tiempo.universe, [1.5, 2.5, 3.5])
tiempo['mucha'] = fuzz.smf(tiempo.universe, 2.0, 3.5)
return agua, cafe, leche, chocolate, tiempo
def __init__(self):
"""Initialize of the FlightPhase object."""
super(FlightPhase, self).__init__()
# logic states
self.alt_range = np.arange(0, 40000, 1)
self.roc_range = np.arange(-4000, 4000, 0.1)
self.spd_range = np.arange(0, 600, 1)
self.states = np.arange(0, 6, 0.01)
self.alt_gnd = fuzz.zmf(self.alt_range, 0, 200)
self.alt_lo = fuzz.gaussmf(self.alt_range, 10000, 10000)
self.alt_hi = fuzz.gaussmf(self.alt_range, 35000, 20000)
self.roc_zero = fuzz.gaussmf(self.roc_range, 0, 100)
self.roc_plus = fuzz.smf(self.roc_range, 10, 1000)
self.roc_minus = fuzz.zmf(self.roc_range, -1000, -10)
self.spd_hi = fuzz.gaussmf(self.spd_range, 600, 100)
self.spd_md = fuzz.gaussmf(self.spd_range, 300, 100)
self.spd_lo = fuzz.gaussmf(self.spd_range, 0, 50)
self.state_ground = fuzz.gaussmf(self.states, 1, 0.1)
self.state_climb = fuzz.gaussmf(self.states, 2, 0.1)
self.state_descent = fuzz.gaussmf(self.states, 3, 0.1)
self.state_cruise = fuzz.gaussmf(self.states, 4, 0.1)
self.state_level = fuzz.gaussmf(self.states, 5, 0.1)
self.state_lable_map = {1: 'GND', 2: 'CL', 3: 'DE', 4: 'CR', 5: 'LVL'}
self.ts = None
self.alt = None
self.spd = None
self.roc = None
def fuzzify_direc_val(self, direc_vals, stop_vals):
direc_f = fuzzy.trimf(direc_vals, [-1, 0, 1])
direc_l = fuzzy.zmf(direc_vals, -1, 0)
direc_r = 1.0 - fuzzy.zmf(direc_vals, 0, 1)
stop = 1.0 - fuzzy.zmf(stop_vals, 0.5, 1.5)
return direc_f, direc_l, direc_r, stop
def calculate_pi3k_mfs(egfr, erk, pi3k): egfr_low = fuzz.zmf(egfr, 0, 0.95) egfr_high = fuzz.smf(egfr, 0.1, 0.9) erk_low = fuzz.zmf(erk, 0, 0.9) erk_high = fuzz.smf(erk, 0, 0.9) pi3k_low = fuzz.gaussmf(pi3k, 0, egfr[egfr.size - 1]/20) pi3k_high = fuzz.gaussmf(pi3k, egfr[egfr.size - 1], egfr[egfr.size - 1]/20) return ((egfr_low, egfr_high), (erk_low, erk_high), (pi3k_low, pi3k_high))
def calculate_raf_mfs( egfr, akt, raf): egfr_low = fuzz.zmf(egfr, 0, 0.95) egfr_high = fuzz.smf(egfr, 0.1, 0.9) akt_low = fuzz.zmf(akt, 0, 0.95) akt_high = fuzz.smf(akt, 0.1, 0.9) raf_low = fuzz.gaussmf(raf, 0, egfr[egfr.size - 1]/20) raf_high = fuzz.gaussmf(raf, egfr[egfr.size - 1], egfr[egfr.size - 1]/20) return ((egfr_low, egfr_high), (akt_low, akt_high), (raf_low, raf_high))
def membership_f(mf, x, abcd):
"""
Returns y values corresponding to type of type of Membership fn.
arguments:
mf - string containing type of Membership function
x - x axis values
"""
if mf == "zmf":
return fuzz.zmf(x, abcd[0], abcd[1]) # zmf(x, a, b)
elif mf == "trimf":
return fuzz.trimf(x, abcd[0:3]) # trimf(x, abc)
elif mf == "dsigmf":
return fuzz.dsigmf(x, abcd[0], abcd[1], abcd[2], abcd[3]) # dsigmf(x, b1, c1, b2, c2)
elif mf == "gauss2mf":
return fuzz.gauss2mf(x, abcd[0], abcd[1], abcd[2], abcd[3]) # gauss2mf(x, mean1, sigma1, mean2, sigma2)
elif mf == "gaussmf":
return fuzz.gaussmf(x, abcd[0], abcd[1]) # gaussmf(x, mean, sigma)
elif mf == "gbellmf":
return fuzz.gbellmf(x, abcd[0], abcd[1], abcd[2]) # gbellmf(x, a, b, c)
elif mf == "piecemf":
return fuzz.piecemf(x, abcd[0:3]) # piecemf(x, abc)
elif mf == "pimf":
return fuzz.pimf(x, abcd[0], abcd[1], abcd[2], abcd[3]) # pimf(x, a, b, c, d)
elif mf == "psigmf":
return fuzz.psigmf(x, abcd[0], abcd[1], abcd[2], abcd[3]) # psigmf(x, b1, c1, b2, c2)
elif mf == "sigmf":
return fuzz.sigmf(x, abcd[0], abcd[1]) # sigmf(x, b, c)
elif mf == "smf":
return fuzz.smf(x, abcd[0], abcd[1]) # smf(x, a, b)
elif mf == "trapmf":
return fuzz.trapmf(x, abcd) # trapmf(x, abcd)
def EcHistDifuso(img):
gris = np.uint8(color.rgb2gray(cv2.resize(img, (576, 432))) * 255)
fil, col = gris.shape
pixel = np.linspace(0, 255, 256)
oscuros = fuzzy.zmf(
pixel, 25, 130
) #Conjunto difuzo tipo Z, en el 25 empieza a caer, y cae hasta 130, luego es 0
claros = fuzzy.smf(pixel, 130, 230)
grises = fuzzy.gbellmf(
pixel, 55, 3, 128) #Apertura de campana, pendiente de caída, centro
s1 = 10
s2 = 128
s3 = 245
newg = np.zeros(256)
for i in range(256):
newg[i] = (oscuros[i] * s1 + grises[i] * s2 +
claros[i] * s3) / (oscuros[i] + grises[i] + claros[i])
ehf = np.zeros([fil, col])
for ff in range(fil):
for cc in range(col):
valor = gris[ff, cc]
ehf[ff, cc] = newg[valor]
ehf = np.uint8(ehf)
#Se salva el archivo
path_file = ('static/%s.jpg' % uuid.uuid4().hex)
io.imsave(path_file, ehf)
return json.dumps(path_file) #Regresa el nombre de la imagen
def membership_f(mf, x, abcd):
"""
Returns y values corresponding to type of type of Membership fn.
arguments:
mf - string containing type of Membership function
x - x axis values
"""
if mf == 'zmf': return fuzz.zmf(x, abcd[0], abcd[1]) # zmf(x, a, b)
elif mf == 'trimf': return fuzz.trimf(x, abcd[0:3]) # trimf(x, abc)
elif mf == 'dsigmf':
return fuzz.dsigmf(x, abcd[0], abcd[1], abcd[2],
abcd[3]) # dsigmf(x, b1, c1, b2, c2)
elif mf == 'gauss2mf':
return fuzz.gauss2mf(
x, abcd[0], abcd[1], abcd[2],
abcd[3]) # gauss2mf(x, mean1, sigma1, mean2, sigma2)
elif mf == 'gaussmf':
return fuzz.gaussmf(x, abcd[0], abcd[1]) # gaussmf(x, mean, sigma)
elif mf == 'gbellmf':
return fuzz.gbellmf(x, abcd[0], abcd[1],
abcd[2]) # gbellmf(x, a, b, c)
elif mf == 'piecemf':
return fuzz.piecemf(x, abcd[0:3]) # piecemf(x, abc)
elif mf == 'pimf':
return fuzz.pimf(x, abcd[0], abcd[1], abcd[2],
abcd[3]) # pimf(x, a, b, c, d)
elif mf == 'psigmf':
return fuzz.psigmf(x, abcd[0], abcd[1], abcd[2],
abcd[3]) # psigmf(x, b1, c1, b2, c2)
elif mf == 'sigmf':
return fuzz.sigmf(x, abcd[0], abcd[1]) # sigmf(x, b, c)
elif mf == 'smf':
return fuzz.smf(x, abcd[0], abcd[1]) # smf(x, a, b)
elif mf == 'trapmf':
return fuzz.trapmf(x, abcd) # trapmf(x, abcd)
def get_fuzzy_membership_map():
normal_trapezoid = np_array([120, 280, 320, 500])
return {
Cost.CHEAP: lambda x: zmf(x, a=0, b=180),
Cost.NORMAL: lambda x: trapmf(x, abcd=normal_trapezoid),
Cost.EXPENSIVE: lambda x: smf(x, a=300, b=1000)
}
def calculate_egfr_mfs(time, egf, egfr, egf_index, t): size = egf.size #egfr = np.linspace(0, egf[egf_index], size) time_low = fuzz.zmf(time, 0, time[egf.size*t - t] - time[egf_index*t] + time[t] ) time_high = fuzz.smf(time, 0, time[egf.size*t - t] - time[egf_index*t] + time[t] ) egfr_low = fuzz.gaussmf(egfr, 0, egf[egf_index]/20) egfr_high = transform_gaussmf(egfr, (egf[egf_index], egf[egf_index]/20), 1) return ((time_low, time_high, egfr_low, egfr_high))
def get_fuzzy_membership_map():
average_trapezoid = np_array([10, 48, 52, 90])
return {
Distance.SHORT: lambda x: zmf(x, a=0, b=30),
Distance.AVERAGE: lambda x: trapmf(x, abcd=average_trapezoid),
Distance.LONG: lambda x: smf(x, a=20, b=100)
}
def antecedentes():
temperatura = ctrl.Antecedent(np.arange(-10, 41, 1), 'temperatura')
tazaSize = ctrl.Antecedent(
[0, 30, 60, 90, 120, 150, 200, 250, 300, 350, 400, 450, 451],
'tazaSize')
intensidad = ctrl.Antecedent(np.arange(1, 6, 1), 'intensidad')
temperatura['frio'] = fuzz.zmf(temperatura.universe, -10, 41)
temperatura['calido'] = fuzz.gaussmf(temperatura.universe, 18, 10)
temperatura['caluroso'] = fuzz.smf(temperatura.universe, -11, 41)
tazaSize['pequeno'] = fuzz.zmf(tazaSize.universe, 0, 451)
tazaSize['mediano'] = fuzz.gaussmf(tazaSize.universe, 240, 100)
tazaSize['grande'] = fuzz.smf(tazaSize.universe, 0, 451)
intensidad['suave'] = fuzz.zmf(intensidad.universe, 0, 5)
intensidad['medio'] = fuzz.gaussmf(intensidad.universe, 3, 1)
intensidad['fuerte'] = fuzz.smf(intensidad.universe, 0, 5)
return temperatura, tazaSize, intensidad
def _makeMemberFunctions(x):
"""
Returns matrix of member functions values for given universal set.
Rows denote values for following terms: Low, Medium, High.
"""
half = x[x.size // 2]
return np.vstack((fz.zmf(x, x[0], half), fz.trimf(x, [x[0], half, x[-1]]),
fz.smf(x, half, x[-1])))
def membership_f(mf, x, abc = [0,0,0], a = 1, b = 2, c = 3, d = 4, abcd = [0,0,0,0]):
return {
'trimf' : fuzz.trimf(x, abc), # trimf(x, abc)
'dsigmf' : fuzz.dsigmf(x, a, b, c, d), # dsigmf(x, b1, c1, b2, c2)
'gauss2mf': fuzz.gauss2mf(x, a, b, c, d), # gauss2mf(x, mean1, sigma1, mean2, sigma2)
'gaussmf' : fuzz.gaussmf(x, a, b), # gaussmf(x, mean, sigma)
'gbellmf' : fuzz.gbellmf(x, a, b, c), # gbellmf(x, a, b, c)
'piecemf' : fuzz.piecemf(x, abc), # piecemf(x, abc)
'pimf' : fuzz.pimf(x, a, b, c, d), # pimf(x, a, b, c, d)
'psigmf' : fuzz.psigmf(x, a, b, c, d), # psigmf(x, b1, c1, b2, c2)
'sigmf' : fuzz.sigmf(x, a, b), # sigmf(x, b, c)
'smf' : fuzz.smf(x, a, b), # smf(x, a, b)
'trapmf' : fuzz.trapmf(x, abcd), # trapmf(x, abcd)
'zmf' : fuzz.zmf(x, a, b), # zmf(x, a, b)
}[mf]
def get_terms(individual):
terms_individual = []
for attribute in individual:
terms_num = len(attribute)
terms = []
for i in range(terms_num):
numbers = np.arange(0, attribute[i][1] + 1, 1)
if 0 < i < terms_num - 1:
term_numbers = attribute[i][0]
term_numbers.sort()
term = fuzz.trapmf(numbers, term_numbers)
elif i == 0:
term = fuzz.zmf(numbers, attribute[i][0][0], attribute[i][1])
else:
term = fuzz.smf(numbers, attribute[i][0][0], attribute[i][1])
terms.append(term)
terms_individual.append(terms)
return terms_individual
def eval_membership_functions(initial_values): '''Technically they should have been calcultated using fuzz.someMf but since they are same to save computation we do this''' egf_high = fuzz.gaussmf(initial_values[0], 1, 0.1) egf_low = fuzz.gaussmf(initial_values[0], 0, 0.1) hrg_high = egf_high hrg_low = egf_low egfr_high = egf_high egfr_low = egf_low erk_high = egfr_high erk_low = egfr_low pi3k_high = egfr_high pi3k_low = egfr_low akt_high = egfr_high akt_low = egfr_low raf_high = egfr_high raf_low = egfr_low time_high = fuzz.smf(initial_values[7], 0, 1) time_low = fuzz.zmf(initial_values[7], 0, 1) return ((egf_low, egf_high), (hrg_low, hrg_high), (egfr_low, egfr_high), (raf_low, raf_high), (pi3k_low, pi3k_high), (erk_low, erk_high), \ (akt_low, akt_high), (time_low, time_high))
def membership_f(mf, x, abc = [0,0,0], a = 1, b = 2, c = 3, d = 4, abcd = [0,0,0,0]):
"""
Returns y values corresponding to type of type of Membership fn.
arguments:
mf - string containing type of Membership function
x - x axis values
abc - list containing triangular edge point x-values
"""
return {
'trimf' : fuzz.trimf(x, abc), # trimf(x, abc)
'dsigmf' : fuzz.dsigmf(x, a, b, c, d), # dsigmf(x, b1, c1, b2, c2)
'gauss2mf': fuzz.gauss2mf(x, a, b, c, d), # gauss2mf(x, mean1, sigma1, mean2, sigma2)
'gaussmf' : fuzz.gaussmf(x, a, b), # gaussmf(x, mean, sigma)
'gbellmf' : fuzz.gbellmf(x, a, b, c), # gbellmf(x, a, b, c)
'piecemf' : fuzz.piecemf(x, abc), # piecemf(x, abc)
'pimf' : fuzz.pimf(x, a, b, c, d), # pimf(x, a, b, c, d)
'psigmf' : fuzz.psigmf(x, a, b, c, d), # psigmf(x, b1, c1, b2, c2)
'sigmf' : fuzz.sigmf(x, a, b), # sigmf(x, b, c)
'smf' : fuzz.smf(x, a, b), # smf(x, a, b)
'trapmf' : fuzz.trapmf(x, abcd), # trapmf(x, abcd)
'zmf' : fuzz.zmf(x, a, b), # zmf(x, a, b)
}[mf]
def membership_f(mf, x, abc=[0, 0, 0], a=1, b=2, c=3, d=4, abcd=[0, 0, 0, 0]):
"""
Returns y values corresponding to type of type of Membership fn.
arguments:
mf - string containing type of Membership function
x - x axis values
abc - list containing triangular edge point x-values
"""
return {
"trimf": fuzz.trimf(x, abc), # trimf(x, abc)
"dsigmf": fuzz.dsigmf(x, a, b, c, d), # dsigmf(x, b1, c1, b2, c2)
"gauss2mf": fuzz.gauss2mf(x, a, b, c, d), # gauss2mf(x, mean1, sigma1, mean2, sigma2)
"gaussmf": fuzz.gaussmf(x, a, b), # gaussmf(x, mean, sigma)
"gbellmf": fuzz.gbellmf(x, a, b, c), # gbellmf(x, a, b, c)
"piecemf": fuzz.piecemf(x, abc), # piecemf(x, abc)
"pimf": fuzz.pimf(x, a, b, c, d), # pimf(x, a, b, c, d)
"psigmf": fuzz.psigmf(x, a, b, c, d), # psigmf(x, b1, c1, b2, c2)
"sigmf": fuzz.sigmf(x, a, b), # sigmf(x, b, c)
"smf": fuzz.smf(x, a, b), # smf(x, a, b)
"trapmf": fuzz.trapmf(x, abcd), # trapmf(x, abcd)
"zmf": fuzz.zmf(x, a, b), # zmf(x, a, b)
}[mf]
def __init__(self, p, n_variavel, tipo='antecedente'):
# p: probabilidade de evento favorável.
# n_variavel: nome da variavel.
# tipo: tipo de variável fuzzy.
self.min = 0
self.max = 1
# Estima a média e o desvio padrão.
self.media = p
self.dp = (p * (1 - p))**0.5
if tipo == 'consequente':
# O passo foi padronizado em 0.01.
self.vf = ctrl.Consequent(np.arange(0, 1, 0.01), n_variavel)
else:
self.vf = ctrl.Antecedent(np.arange(0, 1, 0.01), n_variavel)
# Escala Likert padronizada por 3 categorias para uma binomial normalizada.
self.vf['baixo'] = fuzz.zmf(self.vf.universe, 0, p)
self.vf['medio'] = fuzz.gaussmf(self.vf.universe, p, self.dp)
self.vf['alto'] = fuzz.smf(self.vf.universe, p, 1)
# Trapezoidal membership function trapmf = fuzz.trapmf(x, [0, 2, 8, 10]) # Sigmoid membership function center = 5.0 width_control = 2.0 sigmf = fuzz.sigmf(x, center, width_control) # S-function foot = 1.0 ceiling = 9.0 smf = fuzz.smf(x, foot, ceiling) # Z-function zmf = fuzz.zmf(x, foot, ceiling) # Pi-function pimf = fuzz.pimf(x, 0.0, 4.0, 5.0, 10.0) # Gaussian function mean = 5.0 sigma = 1.25 gaussmf = fuzz.gaussmf(x, mean, sigma) # Generalized Bell-Shaped function width = 2.0 slope = 4.0 center = 5.0 gbellmf = fuzz.gbellmf(x, width, slope, center)
def calculate_akt_mfs(pi3k, akt): pi3k_low = fuzz.zmf(pi3k, 0, 0.95) pi3k_high = fuzz.smf(pi3k, 0, 0.9) akt_low = fuzz.gaussmf(akt, 0, akt[akt.size -1]/20) akt_high = fuzz.gaussmf(akt, akt[akt.size -1], akt[akt.size -1]/20) return ((pi3k_low, pi3k_high), (akt_low, akt_high))
# * Quality and service on subjective ranges [0, 10]
# * Tip has a range of [0, 25] in units of percentage points
x_qual = np.arange(0, 11, 1)
x_serv = np.arange(0, 11, 1)
x_tip = np.arange(0, 26, 1)
# Generate fuzzy membership functions
qual_lo = fuzz.gaussmf(x_qual, 3, 0.5)
qual_md = fuzz.gbellmf(x_qual, 1, 1, 5)
qual_hi = fuzz.piecemf(x_qual, [6, 7, 10])
serv_lo = fuzz.pimf(x_serv, 0, 2.9, 3, 8)
serv_md = fuzz.sigmoid(x_serv, 0.5)
serv_hi = fuzz.smf(x_serv, 6, 9)
tip_lo = fuzz.trapmf(x_tip, [0, 0, 3, 6])
tip_md = fuzz.trimf(x_tip, [0, 13, 25])
tip_hi = fuzz.zmf(x_tip, 14, 20)
# Visualize these universes and membership functions
fig, (ax0, ax1, ax2) = plt.subplots(nrows=3, figsize=(8, 9))
ax0.plot(x_qual, qual_lo, 'b', linewidth=1.5, label='Bad')
ax0.plot(x_qual, qual_md, 'g', linewidth=1.5, label='Decent')
ax0.plot(x_qual, qual_hi, 'r', linewidth=1.5, label='Great')
ax0.set_title('Food quality')
ax0.legend()
ax1.plot(x_serv, serv_lo, 'b', linewidth=1.5, label='Poor')
ax1.plot(x_serv, serv_md, 'g', linewidth=1.5, label='Acceptable')
ax1.plot(x_serv, serv_hi, 'r', linewidth=1.5, label='Amazing')
ax1.set_title('Service quality')
ax1.legend()
import numpy as np import skfuzzy as fuzz from matplotlib import pyplot as plt from scipy import stats from filters import SavitzkyGolay # margin of outputs rules determin if a state is a valid state STATE_DIFF_MARGIN = 0.2 # logic states alt_range = np.arange(0, 40000, 1) dh_range = np.arange(-20, 20, 0.1) spd_range = np.arange(0, 600, 1) states = np.arange(0, 5, 0.01) alt_gnd = fuzz.zmf(alt_range, 0, 200) alt_lo = fuzz.gaussmf(alt_range, 10000, 10000) alt_hi = fuzz.gaussmf(alt_range, 30000, 10000) dh_zero = fuzz.gaussmf(dh_range, 0, 5) dh_plus = fuzz.sigmf(dh_range, 6, 1) dh_minus = fuzz.sigmf(dh_range, -6, -1) spd_hi = fuzz.gaussmf(spd_range, 600, 200) spd_md = fuzz.gaussmf(spd_range, 100, 100) spd_lo = fuzz.gaussmf(spd_range, 0, 50) state_ground = fuzz.gaussmf(states, 1, 0.1) state_climb = fuzz.gaussmf(states, 2, 0.1) state_descend = fuzz.gaussmf(states, 3, 0.1) state_cruise = fuzz.gaussmf(states, 4, 0.1)
""" # Commented out IPython magic to ensure Python compatibility. # %matplotlib inline import numpy as np import skfuzzy as fuzz import matplotlib.pyplot as plt from skfuzzy import control as ctrl temperature = ctrl.Antecedent(np.arange(0, 41, 1), 'temperature') humidity = ctrl.Antecedent(np.arange(0, 100, 1), 'humidity') light = ctrl.Antecedent(np.arange(0, 1000, 1), 'light') survivability = ctrl.Consequent(np.arange(0, 90, 1), 'survivability') temperature['cold'] = fuzz.zmf(temperature.universe, 0, 17) temperature['warm'] = fuzz.trimf(temperature.universe, [13, 28, 34]) temperature['hot'] = fuzz.trimf(temperature.universe, [30, 40, 41]) humidity['wet'] = fuzz.trimf(humidity.universe, [65, 100, 100]) humidity['moist'] = fuzz.trimf(humidity.universe, [15, 50, 70]) humidity['dry'] = fuzz.zmf(humidity.universe, 0, 20) light['low'] = fuzz.zmf(light.universe, 0, 300) light['good'] = fuzz.trimf(light.universe, [250, 650, 900]) light['high'] = fuzz.trimf(light.universe, [800, 1000, 1000]) survivability['very low'] = fuzz.trimf(survivability.universe, [0, 0, 15]) survivability['low'] = fuzz.trimf(survivability.universe, [15, 20, 30]) survivability['pretty'] = fuzz.trimf(survivability.universe, [30, 35, 45]) survivability['good'] = fuzz.trimf(survivability.universe, [45, 55, 75])
from collections import namedtuple
from numpy import arange
from skfuzzy import control, trapmf, smf, zmf
state_health = control.Antecedent(arange(0, 100, 1), 'state_health')
state_health.automf(number=3, names=['bad', 'good', 'excellent'])
calories = control.Antecedent(arange(0, 5000, 1), 'calories')
universe = calories.universe
calories['little'] = zmf(universe, 1000, 1300)
calories['enough'] = trapmf(universe, [1000, 1100, 1800, 2100])
calories['lot'] = smf(universe, 2000, 2300)
training_experience = control.Antecedent(arange(0, 20, 1), 'training_experience')
universe = training_experience.universe
training_experience['small'] = zmf(universe, 1, 4)
training_experience['medium'] = trapmf(universe, [3, 4, 8, 12])
training_experience['large'] = smf(universe, 10, 15)
decision = control.Consequent(arange(0, 20, 1), 'decision')
decision.automf(number=3, names=['low', 'middle', 'high'])
prereq_one = (
state_health['bad']
& (calories['little'] | calories['enough'])
& (training_experience['small'] | training_experience['medium'])
)
rule_one = control.Rule(prereq_one, decision['low'])
prereq_two = (
def eval_membership_function_egf(egf_values): '''Evaluates membership function for egf ''' egf_high = fuzz.smf(egf_values, 0, 1) egf_low = fuzz.zmf(egf_values, 0, 1) return (egf_low, egf_high)
# Calcular rangos de [HumMin, HumMax] y [HumCrit, HumMin]
hum_min_max = abs(hum_min - hum_max)
hum_min_crit = abs(hum_crit - hum_min)
# Valores del riego
values = np.array([0.0, 0.5, 1.0, 1.5])
# Rangos de valores para cada modelo difuso
x_hum = np.arange(1024)
x_lum = np.arange(1001)
x_tmp = np.arange(100)
x_reg = np.linspace(0.0, 1.5, 16)
# Establecer conjuntos difusos
hum_hi = fuzz.zmf(x_hum, hum_max - hum_min_max / 4, hum_max)
hum_md = fuzz.trapmf(
x_hum,
[hum_max - hum_min_max / 4, hum_max, hum_min, hum_min + hum_min_crit / 2])
hum_lo = fuzz.smf(x_hum, hum_min + hum_min_crit / 3, hum_crit)
lum_lo = fuzz.zmf(x_lum, lum_min - 50, lum_min)
lum_md = fuzz.trapmf(x_lum, [lum_min - 50, lum_min, lum_max, lum_max + 50])
lum_hi = fuzz.smf(x_lum, lum_max, lum_max + 50)
tmp_lo = fuzz.zmf(x_tmp, tmp_min - 5, tmp_min)
tmp_md = fuzz.trapmf(x_tmp, [tmp_min - 5, tmp_min, tmp_max, tmp_crit])
tmp_hi = fuzz.smf(x_tmp, tmp_max, tmp_crit)
reg_no = fuzz.trimf(x_reg, [0.0, 0.0, 0.5])
reg_lo = fuzz.trimf(x_reg, [0.0, 0.5, 1.0])
import numpy as np import skfuzzy as fuzz from matplotlib import pyplot as plt from scipy.interpolate import UnivariateSpline # margin of outputs rules determin if a state is a valid state STATE_DIFF_MARGIN = 0.2 # logic states alt_range = np.arange(0, 40000, 1) roc_range = np.arange(-4000, 4000, 0.1) spd_range = np.arange(0, 600, 1) states = np.arange(0, 6, 0.01) alt_gnd = fuzz.zmf(alt_range, 0, 200) alt_lo = fuzz.gaussmf(alt_range, 10000, 5000) alt_hi = fuzz.gaussmf(alt_range, 35000, 20000) roc_zero = fuzz.gaussmf(roc_range, 0, 100) roc_plus = fuzz.smf(roc_range, 10, 1000) roc_minus = fuzz.zmf(roc_range, -1000, -10) spd_hi = fuzz.gaussmf(spd_range, 600, 100) spd_md = fuzz.gaussmf(spd_range, 200, 100) spd_lo = fuzz.gaussmf(spd_range, 0, 50) state_ground = fuzz.gaussmf(states, 1, 0.1) state_climb = fuzz.gaussmf(states, 2, 0.1) state_descent = fuzz.gaussmf(states, 3, 0.1) state_cruise = fuzz.gaussmf(states, 4, 0.1) state_level = fuzz.gaussmf(states, 5, 0.1)
import numpy as np import skfuzzy as fuzz import matplotlib.pyplot as plt from skfuzzy import control as ctrl weather = ctrl.Antecedent(np.arange(-30, 60, 0.1), 'weather') bloodSugar = ctrl.Antecedent(np.arange(30, 1000,0.1), 'bloodSugar') wool = ctrl.Consequent(np.arange(0, 100, 0.1), 'wool') cotton = ctrl.Consequent(np.arange(0, 100,0.1), 'cotton') color = ctrl.Consequent(np.arange(0,255, 0.1), 'color') weather['cold'] = fuzz.zmf(weather.universe, -30,15) weather['warm'] = fuzz.gaussmf(weather.universe, 15,25) weather['hot'] = fuzz.smf(weather.universe, 25, 60) bloodSugar['hypoglycemia'] = fuzz.zmf(bloodSugar.universe, 0, 70) bloodSugar['normal'] = fuzz.gaussmf(bloodSugar.universe, 70, 100) bloodSugar['hyperglycemia'] = fuzz.smf(bloodSugar.universe, 100, 1000) wool['low'] = fuzz.trimf(wool.universe, [0, 0, 33]) wool['medium'] = fuzz.trimf(wool.universe, [0, 33, 66]) wool['high'] = fuzz.trimf(wool.universe, [33, 66, 100]) cotton['low'] = fuzz.trimf(cotton.universe, [0, 0, 33]) cotton['medium'] = fuzz.trimf(cotton.universe, [0, 33, 66]) cotton['high'] = fuzz.trimf(cotton.universe, [33, 66, 100]) color['black'] = fuzz.trimf(color.universe, [0, 0, 100]) color['greys'] = fuzz.trimf(color.universe, [100,100,200]) color['white'] = fuzz.trimf(color.universe, [150,150,255])
def get_fuzzy_membership_map():
return {
Free.FREE: lambda x: zmf(x, a=0, b=6),
Free.NOT_FREE: lambda x: smf(x, a=2, b=10)
}
def geo_fuzzy_lingvo_scale(objects, cluster_id):
percentage = 0
average_profit = 0
profit_by_type = {geo_frame.columns[2]: 0, geo_frame.columns[3]: 0, geo_frame.columns[4]: 0}
for row, series in geo_frame.iterrows():
if row not in objects:
continue
average_profit += int(series[0])
percentage += int(series[1])
profit_by_type[geo_frame.columns[2]] += int(series[2])
profit_by_type[geo_frame.columns[3]] += int(series[3])
profit_by_type[geo_frame.columns[4]] += int(series[4])
for key in profit_by_type.keys():
profit_by_type[key] /= len(objects)
dominating_type = get_dominating_type(profit_by_type)
average_profit = round(average_profit / len(objects))
percentage = round(percentage / len(objects), 2)
# Generate universe variables
x_tendency = np.arange(0, 100, 1)
# Generate fuzzy membership functions
mfn_insignificant = fuzz.zmf(x_tendency, 0, 5)
mfn_low = fuzz.trimf(x_tendency, [5, 30, 30])
mfn_middle = fuzz.trimf(x_tendency, [30, 65, 65])
mfn_main = fuzz.trimf(x_tendency, [65, 100, 100])
# Visualize these universes and membership functions
fig, ax = plt.subplots(nrows=1, figsize=(8, 3))
ax.plot(x_tendency, mfn_insignificant, "r", linewidth=2.5, label="незначительная")
ax.plot(x_tendency, mfn_low, "r", linewidth=1, label="малая")
ax.plot(x_tendency, mfn_middle, "grey", linewidth=1, label="средняя")
ax.plot(x_tendency, mfn_main, "g", linewidth=1, label="основная")
ax.set_title("Доля выручки сегмента Big Data")
ax.legend()
# Turn off top/right axes
ax.spines["top"].set_visible(False)
ax.spines["right"].set_visible(False)
ax.get_xaxis().tick_bottom()
ax.get_yaxis().tick_left()
plt.tight_layout()
fig.savefig("output/geo_fuzzy_scale.png")
# Interpretation
interp_insignificant = fuzz.interp_membership(x_tendency, mfn_insignificant, percentage)
interp_low = fuzz.interp_membership(x_tendency, mfn_low, percentage)
interp_middle = fuzz.interp_membership(x_tendency, mfn_middle, percentage)
interp_main = fuzz.interp_membership(x_tendency, mfn_main, percentage)
activation_insignificant = np.fmin(interp_insignificant, mfn_insignificant)
activation_low = np.fmin(interp_low, mfn_low)
activation_middle = np.fmin(interp_middle, mfn_middle)
activation_main = np.fmin(interp_main, mfn_main)
zeroes = np.zeros_like(x_tendency)
# Visualize this
fig, ax0 = plt.subplots(figsize=(8, 3))
ax0.fill_between(x_tendency, zeroes, activation_insignificant, facecolor="r", alpha=0.7)
ax0.plot(x_tendency, mfn_insignificant, "r", linewidth=2, linestyle="--", )
ax0.fill_between(x_tendency, zeroes, activation_low, facecolor="r", alpha=0.7)
ax0.plot(x_tendency, mfn_low, "r", linewidth=0.5, linestyle="--", )
ax0.fill_between(x_tendency, zeroes, activation_middle, facecolor="grey", alpha=0.7)
ax0.plot(x_tendency, mfn_middle, "grey", linewidth=0.5, linestyle="--")
ax0.fill_between(x_tendency, zeroes, activation_main, facecolor="g", alpha=0.7)
ax0.plot(x_tendency, mfn_main, "g", linewidth=0.5, linestyle="--")
ax0.set_title("Cluster: " + str(cluster_id))
# Turn off top/right axes
ax0.spines["top"].set_visible(False)
ax0.spines["right"].set_visible(False)
ax0.get_xaxis().tick_bottom()
ax0.get_yaxis().tick_left()
img = "geo_fuzzy_" + str(cluster_id) + ".png"
fig.savefig("output/" + img)
# Aggregate all output membership functions together
aggregated = np.fmax(activation_middle,
np.fmax(activation_main,
np.fmax(activation_low, activation_insignificant)))
# Calculate defuzzified result
tendency = fuzz.defuzz(x_tendency, aggregated, 'centroid')
# tendency_activation = fuzz.interp_membership(x_tendency, aggregated, tendency) # for plot
data_for_ui = None, None, None
if tendency <= 5:
data_for_ui = "danger", "glyphicon-arrow-down", "Незначительная"
elif 5 < tendency < 30:
data_for_ui = "danger", "glyphicon-arrow-down", "Малая"
elif 30 <= tendency < 65:
data_for_ui = "default", "glyphicon-minus", "Средняя"
elif 65 <= tendency < 100:
data_for_ui = "success", "glyphicon-arrow-up", "Основная"
return str("%.2f" % tendency), data_for_ui[0], data_for_ui[2], img, average_profit, dominating_type
def calculate_erk_mfs(raf, erk): raf_low = fuzz.zmf(raf, 0, 0.95) raf_high = fuzz.smf(erk, 0.1, 0.9) erk_low = fuzz.gaussmf(erk, 0, raf[raf.size - 1]/20) erk_high = fuzz.gaussmf(erk, raf[raf.size - 1], raf[raf.size - 1]/20) return (raf_low, raf_high, erk_low, erk_high)
def mf_zmf(self, a, t, s):
t = str(self.transform_class_to_target(t))
return fz.zmf(self.ant[a].universe, s['min' + t], s['pke' + t])
def buildFuzzySystem(showDescription=False):
"""
===========================================================================
Build Fuzzy Sistem for variable: memory
===========================================================================
**Args**:
showDescription: (boolean)
**Returns**:
None
"""
#==========================================================================
# Set labels of inputs and outputs
#==========================================================================
var_in1_label = 'memory'
var_out_label = 'out'
logger.info("buildFuzzySystem:" + var_in1_label)
#==========================================================================
# Set numerical range of inputs and outputs
#==========================================================================
in1_max = 100.0
var_in1_universe = np.arange(0, in1_max, in1_max / 1000.0)
var_out_universe = np.arange(0, 1, 0.01)
#==========================================================================
# Set inputs(Antecedent) and outputs (Consequent)
#==========================================================================
var_in1 = ctrl.Antecedent(var_in1_universe, var_in1_label)
var_out = ctrl.Consequent(var_out_universe, var_out_label)
#==========================================================================
# Set membership functions of fuzzy set
#==========================================================================
var_in1.automf(number=3, variable_type='quant')
var_in1['average'] = fuzz.trapmf(
var_in1.universe,
[in1_max * 0.2, in1_max * 0.4, in1_max * 0.8, in1_max * 0.9])
var_in1['high'] = fuzz.smf(var_in1.universe, in1_max * 0.8, in1_max * 0.95)
var_out['low'] = fuzz.zmf(var_out.universe, 0.4, 0.8)
var_out['high'] = fuzz.smf(var_out.universe, 0.7, 0.9)
#==========================================================================
# Set fuzzy rules
#==========================================================================
rule1 = ctrl.Rule(var_in1['high'], var_out['high'])
rule2 = ctrl.Rule(var_in1['low'] | var_in1['average'], var_out['low'])
#==========================================================================
# Build fuzzy control system and simulation
#==========================================================================
var_ctrl = ctrl.ControlSystem([rule1, rule2])
var_fuzzysim = ctrl.ControlSystemSimulation(var_ctrl)
#==========================================================================
# Set fuzzy rules
#==========================================================================
if showDescription:
fig = plt.figure(figsize=(12, 12))
plt.subplot(3, 1, 1)
plt.title('Input: ' + var_in1_label)
plt.plot(var_in1_universe, var_in1['low'].mf, label='low')
plt.plot(var_in1_universe, var_in1['average'].mf, label='average')
plt.plot(var_in1_universe, var_in1['high'].mf, label='high')
plt.legend()
plt.subplot(3, 1, 2)
plt.title('Output: ' + var_out_label)
plt.plot(var_out_universe, var_out['low'].mf, label='low')
plt.plot(var_out_universe, var_out['high'].mf, label='high')
plt.legend()
var_fuzzysim.input[var_in1_label] = var_in1_universe
var_fuzzysim.compute()
y = var_fuzzysim.output[var_out_label]
plt.subplot(3, 1, 3)
plt.plot(var_in1_universe,
y,
label='Fuzzy transform of ' + var_in1_label)
#plt.show()
plt.savefig('/tmp/fuzzy_' + var_in1_label + '.png')
return var_fuzzysim
ax[i].plot([defuzzValue[i], defuzzValue[i]], [0, activation],
'k',
linewidth=1.5,
alpha=0.9)
ax[i].set_title(title[i])
SetAxes(ax)
#--------------------初始化系统------------------------------------
#设置输入与输出变量的论域
amplitude_universe = np.linspace(-1, 1, num=100)
etLoss_universe = np.linspace(0, 0.5, num=100)
etProfit_universe = np.linspace(0, 1, num=100)
# 创建三个模糊隶属函数：一个价格波动幅度（amplitude）输入, 两个输出
amplitude_N_High = fuzz.zmf(amplitude_universe, -0.7, -0.3) #波动幅度为负大
amplitude_N_Medin = fuzz.gaussmf(amplitude_universe, -0.2, 0.1) #波动幅度为负中
amplitude_N_Low = fuzz.gaussmf(amplitude_universe, -0.05, -0.1) #波动幅度为负小
amplitude_P_Low = fuzz.gaussmf(amplitude_universe, 0.05, 0.1) #波动幅度为正小
amplitude_P_Medin = fuzz.gaussmf(amplitude_universe, 0.1, 0.2) #波动幅度为正中
amplitude_P_High = fuzz.smf(amplitude_universe, 0.3, 0.7) #波动幅度为正大
#设置预期损失隶属函数
etLoss_Low = fuzz.gaussmf(etLoss_universe, 0, 0.1)
etLoss_Medin = fuzz.gaussmf(etLoss_universe, 0.2, 0.1)
etLoss_High = fuzz.smf(etLoss_universe, 0.2, 0.4)
#设置预期盈利隶属函数
etProfit_Low = fuzz.gaussmf(etProfit_universe, 0, 0.1)
etProfit_Medin = fuzz.gaussmf(etProfit_universe, 0.2, 0.1)
etProfit_High = fuzz.smf(etProfit_universe, 0.2, 0.4)
#--------------------模糊计算系统------------------------------------
def eval_membership_function_hrg(hrg_values): '''Evaluates membership function for hrg ''' hrg_high = fuzz.smf(hrg_values, 0 , 1) hrg_low = fuzz.zmf(hrg_values, 0, 1) return (hrg_low, hrg_high)
def createFuzzy(self):
self.fuzz_pend1 = ctrl.Antecedent(np.arange(-1.5, 1.6, 0.1), 'join1')
self.fuzz_pend1_v = ctrl.Antecedent(np.arange(-10, 10, 0.1), 'pend1_v')
self.fuzz_motor = ctrl.Consequent(np.arange(-150, 150, 1), 'motor')
self.fuzz_position = ctrl.Antecedent(np.arange(-13, 13, 0.1),
'position')
self.fuzz_vv2 = ctrl.Antecedent(np.arange(-10, 10, 0.1), 'v')
self.fuzz_motor2 = ctrl.Consequent(np.arange(-100, 100, 1), 'motor2')
self.fuzz_pend1['poor'] = fuzz.zmf(self.fuzz_pend1.universe, -0.2,
-0.1)
self.fuzz_pend1['mediocre'] = fuzz.trimf(self.fuzz_pend1.universe,
[-0.2, -0.1, 0])
self.fuzz_pend1['average'] = fuzz.trimf(self.fuzz_pend1.universe,
[-0.1, 0, 0.1])
self.fuzz_pend1['decent'] = fuzz.trimf(self.fuzz_pend1.universe,
[0, 0.1, 0.2])
self.fuzz_pend1['good'] = fuzz.smf(self.fuzz_pend1.universe, 0.1, 0.2)
self.fuzz_pend1_v['poor'] = fuzz.zmf(self.fuzz_pend1_v.universe, -2,
-1)
self.fuzz_pend1_v['mediocre'] = fuzz.trimf(self.fuzz_pend1_v.universe,
[-2, -1, 0])
self.fuzz_pend1_v['average'] = fuzz.trimf(self.fuzz_pend1_v.universe,
[-1, 0, 1])
self.fuzz_pend1_v['decent'] = fuzz.trimf(self.fuzz_pend1_v.universe,
[0, 1, 2])
self.fuzz_pend1_v['good'] = fuzz.smf(self.fuzz_pend1_v.universe, 1, 2)
self.fuzz_motor['poor'] = fuzz.zmf(self.fuzz_motor.universe, -50, -20)
self.fuzz_motor['average'] = fuzz.trimf(self.fuzz_motor.universe,
[-50, 0, 50])
self.fuzz_motor['good'] = fuzz.smf(self.fuzz_motor.universe, 20, 50)
self.fuzz_position['poor'] = fuzz.zmf(self.fuzz_position.universe, -5,
-2)
self.fuzz_position['average'] = fuzz.trimf(self.fuzz_position.universe,
[-5, 0, 5])
self.fuzz_position['good'] = fuzz.smf(self.fuzz_position.universe, 2,
5)
self.fuzz_motor2['poor'] = fuzz.zmf(self.fuzz_motor2.universe, -50,
-20)
self.fuzz_motor2['average'] = fuzz.trimf(self.fuzz_motor2.universe,
[-50, 0, 50])
self.fuzz_motor2['good'] = fuzz.smf(self.fuzz_motor2.universe, 20, 50)
self.fuzz_vv2['poor'] = fuzz.zmf(self.fuzz_vv2.universe, -5, -2.5)
self.fuzz_vv2['average'] = fuzz.trimf(self.fuzz_vv2.universe,
[-5, 0, 5])
self.fuzz_vv2['good'] = fuzz.smf(self.fuzz_vv2.universe, 2.5, 5)
# self.fuzz_pend1['average'].view()
# self.fuzz_pend1_v['average'].view()
# self.fuzz_motor['average'].view()
# self.fuzz_position['average'].view()
# self.fuzz_vv2['average'].view()
# self.fuzz_motor2['average'].view()
self.rule1 = ctrl.Rule(
self.fuzz_pend1['poor'] & self.fuzz_pend1_v['poor'],
self.fuzz_motor['poor'])
self.rule2 = ctrl.Rule(
self.fuzz_pend1['poor'] & self.fuzz_pend1_v['mediocre'],
self.fuzz_motor['poor'])
self.rule3 = ctrl.Rule(
self.fuzz_pend1['poor'] & self.fuzz_pend1_v['average'],
self.fuzz_motor['poor'])
self.rule4 = ctrl.Rule(
self.fuzz_pend1['poor'] & self.fuzz_pend1_v['decent'],
self.fuzz_motor['poor'])
self.rule5 = ctrl.Rule(
self.fuzz_pend1['poor'] & self.fuzz_pend1_v['good'],
self.fuzz_motor['poor'])
self.rule6 = ctrl.Rule(
self.fuzz_pend1['mediocre'] & self.fuzz_pend1_v['poor'],
self.fuzz_motor['poor'])
self.rule7 = ctrl.Rule(
self.fuzz_pend1['mediocre'] & self.fuzz_pend1_v['mediocre'],
self.fuzz_motor['poor'])
self.rule8 = ctrl.Rule(
self.fuzz_pend1['mediocre'] & self.fuzz_pend1_v['average'],
self.fuzz_motor['poor'])
self.rule9 = ctrl.Rule(
self.fuzz_pend1['mediocre'] & self.fuzz_pend1_v['decent'],
self.fuzz_motor['average'])
self.rule10 = ctrl.Rule(
self.fuzz_pend1['mediocre'] & self.fuzz_pend1_v['good'],
self.fuzz_motor['average'])
self.rule11 = ctrl.Rule(
self.fuzz_pend1['average'] & self.fuzz_pend1_v['poor'],
self.fuzz_motor['poor'])
self.rule12 = ctrl.Rule(
self.fuzz_pend1['average'] & self.fuzz_pend1_v['mediocre'],
self.fuzz_motor['poor'])
self.rule13 = ctrl.Rule(
self.fuzz_pend1['average'] & self.fuzz_pend1_v['average'],
self.fuzz_motor['average'])
self.rule14 = ctrl.Rule(
self.fuzz_pend1['average'] & self.fuzz_pend1_v['decent'],
self.fuzz_motor['good'])
self.rule15 = ctrl.Rule(
self.fuzz_pend1['average'] & self.fuzz_pend1_v['good'],
self.fuzz_motor['good'])
self.rule16 = ctrl.Rule(
self.fuzz_pend1['decent'] & self.fuzz_pend1_v['poor'],
self.fuzz_motor['average'])
self.rule17 = ctrl.Rule(
self.fuzz_pend1['decent'] & self.fuzz_pend1_v['mediocre'],
self.fuzz_motor['average'])
self.rule18 = ctrl.Rule(
self.fuzz_pend1['decent'] & self.fuzz_pend1_v['average'],
self.fuzz_motor['good'])
self.rule19 = ctrl.Rule(
self.fuzz_pend1['decent'] & self.fuzz_pend1_v['decent'],
self.fuzz_motor['good'])
self.rule20 = ctrl.Rule(
self.fuzz_pend1['decent'] & self.fuzz_pend1_v['good'],
self.fuzz_motor['good'])
self.rule21 = ctrl.Rule(
self.fuzz_pend1['good'] & self.fuzz_pend1_v['poor'],
self.fuzz_motor['good'])
self.rule22 = ctrl.Rule(
self.fuzz_pend1['good'] & self.fuzz_pend1_v['mediocre'],
self.fuzz_motor['good'])
self.rule23 = ctrl.Rule(
self.fuzz_pend1['good'] & self.fuzz_pend1_v['average'],
self.fuzz_motor['good'])
self.rule24 = ctrl.Rule(
self.fuzz_pend1['good'] & self.fuzz_pend1_v['decent'],
self.fuzz_motor['good'])
self.rule25 = ctrl.Rule(
self.fuzz_pend1['good'] & self.fuzz_pend1_v['good'],
self.fuzz_motor['good'])
self.pendulum_ctrl = ctrl.ControlSystem([
self.rule1, self.rule2, self.rule3, self.rule4, self.rule5,
self.rule6, self.rule7, self.rule8, self.rule9, self.rule10,
self.rule11, self.rule12, self.rule13, self.rule14, self.rule15,
self.rule16, self.rule17, self.rule18, self.rule19, self.rule20,
self.rule21, self.rule22, self.rule23, self.rule24, self.rule25
])
self.pendulum_fuzz = ctrl.ControlSystemSimulation(self.pendulum_ctrl)
self.rule110 = ctrl.Rule(
self.fuzz_vv2['poor'] & self.fuzz_position['poor'],
self.fuzz_motor2['good'])
self.rule111 = ctrl.Rule(
self.fuzz_vv2['poor'] & self.fuzz_position['average'],
self.fuzz_motor2['good'])
self.rule112 = ctrl.Rule(
self.fuzz_vv2['poor'] & self.fuzz_position['good'],
self.fuzz_motor2['average'])
self.rule113 = ctrl.Rule(
self.fuzz_vv2['average'] & self.fuzz_position['poor'],
self.fuzz_motor2['good'])
self.rule114 = ctrl.Rule(
self.fuzz_vv2['average'] & self.fuzz_position['average'],
self.fuzz_motor2['average'])
self.rule115 = ctrl.Rule(
self.fuzz_vv2['average'] & self.fuzz_position['good'],
self.fuzz_motor2['poor'])
self.rule116 = ctrl.Rule(
self.fuzz_vv2['good'] & self.fuzz_position['poor'],
self.fuzz_motor2['average'])
self.rule117 = ctrl.Rule(
self.fuzz_vv2['good'] & self.fuzz_position['average'],
self.fuzz_motor2['poor'])
self.rule118 = ctrl.Rule(
self.fuzz_vv2['good'] & self.fuzz_position['good'],
self.fuzz_motor2['poor'])
self.pendulum_ctrl2 = ctrl.ControlSystem([
self.rule110, self.rule111, self.rule112, self.rule113,
self.rule114, self.rule115, self.rule116, self.rule117,
self.rule118
])
self.pendulum_fuzz2 = ctrl.ControlSystemSimulation(self.pendulum_ctrl2)
def eval_membership_function_time(time_values): '''Evaluates membership function for time ''' time_high = fuzz.smf(time_values, 0, 1) time_low = fuzz.zmf(time_values, 0, 1) return (time_low, time_high)
tabX1.append(float(i))
for i in file['x2']:
tabX2.append(float(i))
for i in file['x3']:
tabX3.append(float(i))
for i in file['y']:
tabY.append(float(i))
# Declare input/output
x1 = ctrl.Antecedent(np.arange(min(tabX1), max(tabX1), 0.001), 'x1')
x2 = ctrl.Antecedent(np.arange(min(tabX2), max(tabX2), 0.001), 'x2')
x3 = ctrl.Antecedent(np.arange(min(tabX3), max(tabX3), 0.001), 'x3')
y = ctrl.Consequent(np.arange(min(tabY), max(tabY), 0.001), 'y')
# Make membership functions
x1['lo'] = fuzz.zmf(x1.universe, min(tabX1), float((max(tabX1) + min(tabX1)) / 2))
x1['md'] = fuzz.gaussmf(x1.universe, float((max(tabX1) + min(tabX1)) / 2), 0.05)
x1['hi'] = fuzz.smf(x1.universe, float((max(tabX1) + min(tabX1)) / 2), max(tabX1))
x2['lo'] = fuzz.zmf(x2.universe, min(tabX2), float((max(tabX2) + min(tabX2)) / 2))
x2['md'] = fuzz.gaussmf(x2.universe, float((max(tabX2) + min(tabX2)) / 2), 0.05)
x2['hi'] = fuzz.smf(x2.universe, float((max(tabX2) + min(tabX2)) / 2), max(tabX2))
x3['lo'] = fuzz.zmf(x3.universe, min(tabX3), float((max(tabX3) + min(tabX3)) / 2))
x3['md'] = fuzz.gaussmf(x3.universe, float((max(tabX3) + min(tabX3)) / 2), 0.05)
x3['hi'] = fuzz.smf(x3.universe, float((max(tabX3) + min(tabX3)) / 2), max(tabX3))
y['lo'] = fuzz.zmf(y.universe, min(tabY), float((max(tabY) + min(tabY)) / 2))
y['md'] = fuzz.gaussmf(y.universe, float((max(tabY) + min(tabY)) / 2), 0.05)
y['hi'] = fuzz.smf(y.universe, float((max(tabY) + min(tabY)) / 2), max(tabY))
import numpy as np import skfuzzy as fuzz from matplotlib import pyplot as plt from scipy import stats from napy.filters import Spline # margin of outputs rules determin if a state is a valid state STATE_DIFF_MARGIN = 0.2 # logic states alt_range = np.arange(0, 40000, 1) roc_range = np.arange(-4000, 4000, 0.1) spd_range = np.arange(0, 600, 1) states = np.arange(0, 6, 0.01) alt_gnd = fuzz.zmf(alt_range, 0, 200) alt_lo = fuzz.gaussmf(alt_range, 10000, 5000) alt_hi = fuzz.gaussmf(alt_range, 35000, 20000) roc_zero = fuzz.gaussmf(roc_range, 0, 100) roc_plus = fuzz.smf(roc_range, 10, 1000) roc_minus = fuzz.zmf(roc_range, -1000, -10) spd_hi = fuzz.gaussmf(spd_range, 600, 100) spd_md = fuzz.gaussmf(spd_range, 200, 100) spd_lo = fuzz.gaussmf(spd_range, 0, 50) state_ground = fuzz.gaussmf(states, 1, 0.1) state_climb = fuzz.gaussmf(states, 2, 0.1) state_descent = fuzz.gaussmf(states, 3, 0.1) state_cruise = fuzz.gaussmf(states, 4, 0.1)
def FuzzyController(autonomy, MSD, time):
# Generate universe variables
# * Quality and service on subjective ranges [0, 10]
# * Tip has a range of [0, 25] in units of percentage points
x_MSD = np.arange(0, 400, 1)
x_autonomy = np.arange(0, 400, 1)
x_time = np.arange(0, 1000, 1)
x_method = np.arange(0, 1, 0.01)
# Generate fuzzy membership functions
MSD_lo = fuzz.zmf(x_MSD, 0, 200)
MSD_md = fuzz.pimf(x_MSD, 100, 150, 250, 300)
MSD_hi = fuzz.smf(x_MSD, 200, 400)
autonomy_lo = fuzz.zmf(x_autonomy, 0, 200)
autonomy_md = fuzz.pimf(x_autonomy, 100, 150, 250, 300)
autonomy_hi = fuzz.smf(x_autonomy, 200, 400)
time_lo = fuzz.zmf(x_time, 0, 500)
time_md = fuzz.pimf(x_time, 250, 400, 600, 750)
time_hi = fuzz.smf(x_time, 500, 1000)
method_lo = fuzz.zmf(x_method, 0, 0.5)
method_md = fuzz.pimf(x_method, 0.25, 0.4, 0.6, 0.75)
method_hi = fuzz.smf(x_method, 0.5, 1)
# We need the activation of our fuzzy membership functions at these values.
# The exact values 6.5 and 9.8 do not exist on our universes...
# This is what fuzz.interp_membership exists for!
autonomy = 100
MSD = 50
time = 800
MSD_level_lo = fuzz.interp_membership(x_MSD, MSD_lo, MSD)
MSD_level_md = fuzz.interp_membership(x_MSD, MSD_md, MSD)
MSD_level_hi = fuzz.interp_membership(x_MSD, MSD_hi, MSD)
autonomy_level_lo = fuzz.interp_membership(x_autonomy, autonomy_lo, autonomy)
autonomy_level_md = fuzz.interp_membership(x_autonomy, autonomy_md, autonomy)
autonomy_level_hi = fuzz.interp_membership(x_autonomy, autonomy_hi, autonomy)
time_level_lo = fuzz.interp_membership(x_time, time_lo, time)
time_level_md = fuzz.interp_membership(x_time, time_md, time)
time_level_hi = fuzz.interp_membership(x_time, time_hi, time)
# Rules
active_rule11 = np.fmin(MSD_level_lo, autonomy_level_lo)
active_rule12 = np.fmax(np.fmin(time_level_lo, autonomy_level_lo), active_rule11)
method_activation_lo = np.fmin(active_rule12, method_lo)
active_rule21 = np.fmin(MSD_level_md, autonomy_level_md)
active_rule22 = np.fmax(np.fmin(time_level_md, autonomy_level_md), active_rule21)
method_activation_md = np.fmin(active_rule22, method_md)
active_rule31 = np.fmin(MSD_level_hi, autonomy_level_hi)
active_rule32 = np.fmax(np.fmin(time_level_hi, autonomy_level_hi), active_rule31)
method_activation_hi = np.fmin(active_rule32, method_hi)
method0 = np.zeros_like(x_method)
# Aggregate all three output membership functions together
aggregated = np.fmax(method_activation_lo,
np.fmax(method_activation_md, method_activation_hi))
# Calculate defuzzified result
method = fuzz.defuzz(x_method, aggregated, 'centroid')
method_activation = fuzz.interp_membership(x_method, aggregated, method) # for plot
method1 = np.arange(method, method + 1, 1)
method_lo1 = fuzz.zmf(method1, 0, 0.5)
method_md1 = fuzz.pimf(method1, 0.25, 0.4, 0.6, 0.75)
method_hi1 = fuzz.smf(method1, 0.5, 1)
stats = {"pot-fields": method_lo1[0], "bio": method_md1[0], "rules": method_hi1[0]}
method = max(stats.items(), key=operator.itemgetter(1))[0]
return method
def fuzzy_lingvo_scale(objects, cluster_id):
mean_growth_times = 0
is_first_iteration = True
for column, series in data_frame.iteritems():
if column not in objects:
continue
series = series.drop("Пространство")
start_value = int(series[0])
end_value = int(series[-1])
growth_times = end_value if start_value == 0 else float(end_value / start_value)
mean_growth_times = growth_times if is_first_iteration else (mean_growth_times + growth_times) / 2
is_first_iteration = False
# Generate universe variables
x_tendency = np.arange(0, 40, 1)
# Generate fuzzy membership functions
mfn_high_fall = fuzz.zmf(x_tendency, 0, 0.5)
mfn_fall = fuzz.trimf(x_tendency, [0.5, 1, 1])
mfn_flat = fuzz.trimf(x_tendency, [1, 2, 2])
mfn_growth = fuzz.trimf(x_tendency, [2, 10, 10])
mfn_high_growth = fuzz.trimf(x_tendency, [10, 40, 40])
# Visualize these universes and membership functions
fig, ax = plt.subplots(nrows=1, figsize=(8, 3))
ax.plot(x_tendency, mfn_high_fall, "r", linewidth=2.5, label="High fall")
ax.plot(x_tendency, mfn_fall, "r", linewidth=1, label="Fall")
ax.plot(x_tendency, mfn_flat, "grey", linewidth=1, label="Flat")
ax.plot(x_tendency, mfn_growth, "g", linewidth=1, label="Growth")
ax.plot(x_tendency, mfn_high_growth, "g", linewidth=2.5, label="High growth")
ax.set_title("Fuzzy scale of trend")
ax.legend()
# Turn off top/right axes
ax.spines["top"].set_visible(False)
ax.spines["right"].set_visible(False)
ax.get_xaxis().tick_bottom()
ax.get_yaxis().tick_left()
plt.tight_layout()
fig.savefig("output/fuzzy_scale.png")
# Interpretation
interp_high_fall = fuzz.interp_membership(x_tendency, mfn_high_fall, mean_growth_times)
interp_fall = fuzz.interp_membership(x_tendency, mfn_fall, mean_growth_times)
interp_flat = fuzz.interp_membership(x_tendency, mfn_flat, mean_growth_times)
interp_growth = fuzz.interp_membership(x_tendency, mfn_growth, mean_growth_times)
interp_high_growth = fuzz.interp_membership(x_tendency, mfn_high_growth, mean_growth_times)
activation_high_fall = np.fmin(interp_high_fall, mfn_high_fall)
activation_fall = np.fmin(interp_fall, mfn_fall)
activation_flat = np.fmin(interp_flat, mfn_flat)
activation_growth = np.fmin(interp_growth, mfn_growth)
activation_high_growth = np.fmin(interp_high_growth, mfn_high_growth)
zeroes = np.zeros_like(x_tendency)
# Visualize this
fig, ax0 = plt.subplots(figsize=(8, 3))
ax0.fill_between(x_tendency, zeroes, activation_high_fall, facecolor="r", alpha=0.7)
ax0.plot(x_tendency, mfn_high_fall, "r", linewidth=2, linestyle="--", )
ax0.fill_between(x_tendency, zeroes, activation_fall, facecolor="r", alpha=0.7)
ax0.plot(x_tendency, mfn_fall, "r", linewidth=0.5, linestyle="--", )
ax0.fill_between(x_tendency, zeroes, activation_flat, facecolor="grey", alpha=0.7)
ax0.plot(x_tendency, mfn_flat, "grey", linewidth=0.5, linestyle="--")
ax0.fill_between(x_tendency, zeroes, activation_growth, facecolor="g", alpha=0.7)
ax0.plot(x_tendency, mfn_growth, "g", linewidth=0.5, linestyle="--")
ax0.fill_between(x_tendency, zeroes, activation_high_growth, facecolor="g", alpha=0.7)
ax0.plot(x_tendency, mfn_high_growth, "g", linewidth=2, linestyle="--")
ax0.set_title("Cluster: " + str(cluster_id) + " | Objects: " + str(objects))
# Turn off top/right axes
ax0.spines["top"].set_visible(False)
ax0.spines["right"].set_visible(False)
ax0.get_xaxis().tick_bottom()
ax0.get_yaxis().tick_left()
plt.tight_layout()
img = "fuzzy_" + str(cluster_id) + ".png"
fig.savefig("output/" + img)
# Aggregate all output membership functions together
aggregated = np.fmax(activation_flat,
np.fmax(activation_growth,
np.fmax(activation_fall,
np.fmax(activation_high_growth, activation_high_fall))))
# Calculate defuzzified result
tendency = fuzz.defuzz(x_tendency, aggregated, 'centroid')
# tendency_activation = fuzz.interp_membership(x_tendency, aggregated, tendency) # for plot
data_for_ui = None, None, None
if tendency <= 0.5:
data_for_ui = "danger", "glyphicon-arrow-down", "High fall"
elif 0 < tendency < 1:
data_for_ui = "danger", "glyphicon-arrow-down", "Fall"
elif 1 <= tendency < 2:
data_for_ui = "default", "glyphicon-minus", "Flat"
elif 2 <= tendency < 10:
data_for_ui = "success", "glyphicon-arrow-up", "Growth"
elif 10 <= tendency <= 40:
data_for_ui = "success", "glyphicon-arrow-up", "High growth"
return str("%.2f" % tendency), data_for_ui[0], data_for_ui[1], data_for_ui[2], img
import numpy as np
import skfuzzy as fuzz
from matplotlib import pyplot as plt
# Problem: from service quality and food quality to tip amount
x_service = np.arange(0, 10.01, 0.5)
x_food = np.arange(0, 10.01, 0.5)
x_tip = np.arange(0, 25.01, 1.0)
# Membership functions
service_low = fuzz.trimf(x_service, [0, 0, 5])
service_middle = fuzz.trimf(x_service, [0, 5, 10])
service_high = fuzz.trimf(x_service, [5, 10, 10])
food_low = fuzz.zmf(x_food, 0, 5)
food_middle = fuzz.pimf(x_food, 0, 4, 5, 10)
food_high = fuzz.smf(x_food, 5, 10)
tip_low = fuzz.trimf(x_tip, [0, 0, 13])
tip_middle = fuzz.trimf(x_tip, [0, 13, 25])
tip_high = fuzz.trimf(x_tip, [13, 25, 25])
# Input: service score and food score
service_score = 9.5
food_score = 4.0
service_low_degree = fuzz.interp_membership(x_service, service_low,
service_score)
service_middle_degree = fuzz.interp_membership(x_service, service_middle,
service_score)
service_high_degree = fuzz.interp_membership(x_service, service_high,
